Tool · Last verified 2026-08-23

Prompt Weight Analyzer

Most production prompts carry weight the model never needed: the same instruction written twice, raw HTML that should have been Markdown, a paragraph of politeness, three blank lines where one would do. On the three samples measured below that overhead runs 27.9%–53.5% of input tokens — and because it is input, it is billed on every single request. Paste a prompt and see where yours goes.

Calculator

Weigh your prompt, category by category

Runs entirely in your browser. Five rule-based checks run in a fixed order, and each reports the tokens it would remove on its own — so the rows add up to the total.

System prompt, user prompt, or both
0input tokens now
0words / segments
0tokens flagged
of prompt flagged
Sample prompts:
CategoryTokensShare of promptVerdict
After trimming0
Cheapest per 1,000 requests, trimmed
Most expensive per 1,000 requests, as written
ModelAs written / 1,000 requestsTrimmed / 1,000 requestsSaved / 1,000 requestsSaved / 100,000 requests
Input only: trimming changes what you send, not what comes back. Private: no upload, no network request. Pricing data verified —
Measured

Three prompts, before and after

Token counts from this site's estimator on the sample prompts loaded by the buttons above. "Flagged" is every category the analyzer would remove, combined.

Sample promptCharactersTokens nowAfter trimFlaggedLargest category
Support system prompt
Duplicated rules, JSON schema, courtesy preamble
1,41231221696 tokens · 30.8%Repeated sentences (48)
RAG prompt with HTMLWorst
Retrieved passages pasted as raw markup
77018787100 tokens · 53.5%Markup tags (48)
Few-shot classifier
Repeated example pairs, one courtesy line
76717212448 tokens · 27.9%Repeated lines (30)

The largest single category differs on every sample, which is the point: there is no universal prompt bloat. Duplicate content dominates when instructions get copy-pasted, markup dominates when a retriever hands back raw HTML, and neither matters on a lean prompt. Run your own before assuming which one applies to you. Counts come from the heuristic estimator used across this site, not a provider tokenizer.

Category detail

What each check actually removes

Five rules, no model calls, no guessing. Each one is a deterministic text transform, so the reported saving is the measured difference, not an estimate on top of an estimate.

CheckWhat it targetsVerdictOn the samples
Excess whitespace
Runs of spaces and tabs, trailing spaces, blank-line piles
Collapses every run to one space and caps blank lines at twoRemove0 – 2 tokens
Repeated sentences
Identical sentences of 25+ characters
Keeps the first occurrence, drops every later oneRemove15 – 48 tokens
Repeated lines
Identical whole lines of 20+ characters
Keeps the first occurrence, drops every later oneRemove18 – 31 tokens
Markup tags
HTML or XML tags, when three or more are present
Strips the tags and leaves the textConvert48 tokens (RAG sample only)
Politeness & hedging
Courtesy preamble and hedging boilerplate
Removes phrases such as "please", "make sure to" and "keep in mind that"Review1 – 28 tokens

Rules are applied in the order shown and each reports its own marginal effect, so a sentence already removed by an earlier check is never counted twice. "Apply safe cleanups" only runs the two removals that cannot change meaning — whitespace and repeated lines — and leaves markup and politeness for you to decide.

Why it compounds

Weight is billed per request, not per prompt.

A single bloated prompt is cheap. The same prompt sent ten thousand times a day is a line item. This is the part that catches teams out: the prompt is written once, reviewed once, and then paid for forever.

Duplication is usually an accident. Instructions get copy-pasted between environments, a rule is restated in both the system prompt and the user turn, and a few-shot example is duplicated by a bad merge. Nothing is wrong functionally, so nobody notices — the tokens just keep billing.

Markup is billed at prose rates. Every <div class="..."> and </h2> costs the same per token as a sentence of the document. On the RAG sample, 48 of 187 input tokens were pure markup.

And the saving scales with the model. On the default support sample, the 96 flagged tokens are worth $0.38 per 1,000 requests on GPT-5.6 Sol and $0.48 on Claude Opus 5 — same tokens, more money, because the percentage applies to a higher rate. At 10,000 requests a day that is $1,752 a year on Opus 5 for text the model never needed.

Written once, paid foreverA 96-token overhead is invisible per request and $1,752 a year at 10,000 requests/day on Opus 5.
Duplication is invisibleRestated rules and copy-pasted examples behave correctly, so no test ever fails.
Markup costs prose rates25.7% of the RAG sample's tokens were tags, not content.
Check the system prompt firstIt is the only part of the request that repeats on 100% of traffic.
Annual cost

What one repeated block costs per year

The arithmetic that makes prompt weight worth measuring: block size × requests per day × 365, priced at published per-1M input rates. Nothing here involves output tokens.

Repeated block1,000 req/day · Sonnet 510,000 req/day · Sonnet 510,000 req/day · Opus 5
10 tokensOne clause
"Answer in English."
$7.30$73.00$182.50
60 tokens
One duplicated rule
$43.80$438.00$1,095.00
200 tokens
A restated policy paragraph
$146.00$1,460.00$3,650.00
500 tokens
An uncached system prompt
$365.00$3,650.00$9,125.00

Computed as tokens × requests/day × 365 ÷ 1,000,000 × rate, at Claude Sonnet 5 ($2.00 per 1M input) and Claude Opus 5 ($5.00 per 1M input), verified 2026-08-09 to 2026-08-16. These are input tokens only and exclude caching, batch and taxes. Note the middle column: the same 500-token block costs $3,650 a year on Sonnet 5 and $9,125 on Opus 5 — which is why trimming matters most on the expensive model, even though the percentage saved is identical.

Caveats

When you should leave the weight in

Not every flagged token is a wasted token. Three cases where trimming is the wrong call.

Politeness can be load-bearing. Removing "please" and "keep in mind that" measurably shifts tone on customer-facing output. Those tokens are flagged Review, not Remove, for exactly this reason — 28 tokens on the support sample is $0.14 per 1,000 requests on Opus 5, which is a fair price for a reply that does not read like a machine.

Duplicates are sometimes deliberate. Restating a constraint at the end of a long prompt genuinely improves adherence, because attention is not uniform across the context. If you removed a duplicate and quality dropped, put it back — the analyzer is reporting cost, not correctness.

Markup may be the subject. If the task is about DOM structure, class names or link targets, stripping the tags destroys the answer. Send a cleaned copy for extraction tasks and keep the markup for structural ones. For a dedicated measurement of that trade-off, use the HTML Token Savings calculator.

RemoveExact duplicates and whitespace — no information is lost.
ConvertMarkup — cheaper as Markdown or plain text, unless structure is the point.
ReviewPoliteness and hedging — cheap to remove, but it changes tone.
Measure afterRe-run the Token Counter on the trimmed prompt before you ship it.
FAQ

Prompt weight questions

How much of a typical prompt is avoidable weight?

On the three sample prompts measured with this site's estimator, 27.9% to 53.5% of input tokens were avoidable: 30.8% on a duplicated customer-support system prompt, 53.5% on a RAG prompt carrying raw HTML passages, and 27.9% on a few-shot classifier with repeated examples. The single largest category differed each time — repeated sentences, markup tags and repeated lines respectively.

Does trimming a prompt change the model's answer?

Removing exact duplicates and markup should not, which is why those categories are marked Remove or Convert. Politeness and hedging phrases are marked Review instead, because deleting them can shift tone. Whitespace removal is marked Remove but moves the fewest tokens of any category.

How much does one repeated instruction actually cost?

A 60-token repeated block sent 10,000 times a day costs $438 per year on Claude Sonnet 5 at $2.00 per million input tokens, and $1,095 per year on Claude Opus 5 at $5.00. A 500-token system prompt you forgot to cache costs $3,650 and $9,125 respectively at the same volume.

Is whitespace worth trimming?

It is the smallest lever. This site's estimator weights a space or newline at 0.08 tokens against roughly 0.25 for a Latin letter, so collapsing runs of whitespace saved 0 to 2 tokens on the three sample prompts. Production tokenizers sometimes bill each space separately, so real savings may be somewhat larger — but repeated instructions and markup are where the weight actually is.

Does this tool upload my prompt?

No. The analysis and the token estimate run entirely in your browser. This page has no form, no backend endpoint, no analytics script and no network requests — paste a proprietary system prompt without it leaving the tab.

Methodology

How these numbers are produced.

Five deterministic text transforms run in a fixed order — collapse whitespace, drop repeated sentences, drop repeated lines, strip markup tags, remove politeness boilerplate — and each reports the token difference it produced on its own. Because the transforms are applied cumulatively and each measures its own marginal effect, the category rows sum exactly to the flagged total, and no token is counted twice. The politeness list is a fixed set of 26 common English courtesy and hedging phrases; it is English-only and will find nothing in a prompt written in another language.

Token counts come from the same heuristic estimator used across this site, which weights CJK characters, emoji, punctuation, whitespace and Latin characters separately — a cross-model approximation, not provider tokenizer output, so real counts differ by a few percent. Cost figures multiply token counts by published per-1M input rates, with OpenAI's long-context surcharge applied automatically above 272,000 input tokens. Output tokens are unaffected by trimming and are excluded. Caching, batch, tool use and taxes are excluded throughout. Rates: OpenAI, Anthropic, Google — verified weekly.

Count any textCharacters, words, tokens and per-model input cost: Token Counter.
Price a workloadTurn token volumes into monthly spend: API Cost Calculator.
Markup-specific savingsMeasure HTML → Markdown conversion on real pages: HTML Token Savings.
Check it still fitsContext Window Checker — windows and output caps for all 8 models.
What a token isDefinition, conversion by content type, and why output costs 5–8x input: What Is an AI Token?
Plan a chunk size100K and 1M tokens in words and pages.
Provider rate cardsOpenAI · Claude · Gemini · all three.